Files
agent-framework/.github/workflows/python-merge-tests.yml
T
Giles Odigwe 733bfb9bfe Bump Ollama model to qwen2.5:1.5b for better instruction following
The 0.5b model was too small to reliably follow simple prompts like
'Say Hello World', causing test assertion failures. The 1.5b model
follows instructions more reliably while still being small enough
for fast CI pulls (~1GB).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-04-23 14:51:16 -07:00

670 lines
24 KiB
YAML

name: Python - Merge - Tests
#
# NOTE: This workflow and python-integration-tests.yml share the same set of
# parallel test jobs. Keep them in sync — when adding, removing, or modifying a
# job here, apply the same change to python-integration-tests.yml.
#
on:
workflow_dispatch:
pull_request:
branches: ["main"]
merge_group:
branches: ["main"]
schedule:
- cron: "0 0 * * *" # Run at midnight UTC daily
permissions:
contents: read
id-token: write
env:
# Configure a constant location for the uv cache
UV_CACHE_DIR: /tmp/.uv-cache
UV_PYTHON: "3.13"
RUN_SAMPLES_TESTS: ${{ vars.RUN_SAMPLES_TESTS }}
jobs:
paths-filter:
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
outputs:
pythonChanges: ${{ steps.filter.outputs.python }}
coreChanged: ${{ steps.filter.outputs.core }}
openaiChanged: ${{ steps.filter.outputs.openai }}
azureChanged: ${{ steps.filter.outputs.azure }}
miscChanged: ${{ steps.filter.outputs.misc }}
functionsChanged: ${{ steps.filter.outputs.functions }}
foundryChanged: ${{ steps.filter.outputs.foundry }}
cosmosChanged: ${{ steps.filter.outputs.cosmos }}
steps:
- uses: actions/checkout@v6
- uses: dorny/paths-filter@v3
id: filter
with:
filters: |
python:
- 'python/**'
- '.github/actions/setup-local-mcp-server/**'
- '.github/workflows/python-merge-tests.yml'
- '.github/workflows/python-integration-tests.yml'
core:
- 'python/packages/core/agent_framework/_*.py'
- 'python/packages/core/agent_framework/_workflows/**'
- 'python/packages/core/agent_framework/exceptions.py'
- 'python/packages/core/agent_framework/observability.py'
openai:
- 'python/packages/core/agent_framework/openai/**'
- 'python/packages/openai/**'
- 'python/samples/**/providers/openai/**'
azure:
- 'python/packages/openai/**'
- 'python/packages/core/agent_framework/azure/**'
- 'python/samples/**/providers/azure/**'
misc:
- 'python/packages/anthropic/**'
- 'python/packages/hyperlight/**'
- 'python/packages/ollama/**'
- 'python/packages/core/agent_framework/_mcp.py'
- 'python/packages/core/tests/core/test_mcp.py'
- 'python/scripts/local_mcp_streamable_http_server.py'
- '.github/actions/setup-local-mcp-server/**'
- '.github/workflows/python-merge-tests.yml'
- '.github/workflows/python-integration-tests.yml'
functions:
- 'python/packages/azurefunctions/**'
- 'python/packages/durabletask/**'
foundry:
- 'python/packages/foundry/**'
- 'python/samples/**/providers/foundry/**'
- 'python/samples/02-agents/embeddings/foundry_embeddings.py'
cosmos:
- 'python/packages/azure-cosmos/**'
# run only if 'python' files were changed
- name: python tests
if: steps.filter.outputs.python == 'true'
run: echo "Python file"
# run only if not 'python' files were changed
- name: not python tests
if: steps.filter.outputs.python != 'true'
run: echo "NOT python file"
# Unit tests: always run all non-integration tests across all packages
python-tests-unit:
name: Python Tests - Unit
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true'
runs-on: ubuntu-latest
environment: integration
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Test with pytest (unit tests only)
run: >
uv run poe test -A
-m "not integration"
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
--junitxml=pytest.xml
working-directory: ./python
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: Unit test results
# OpenAI integration tests
python-tests-openai:
name: Python Tests - OpenAI Integration
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true' &&
(github.event_name != 'merge_group' ||
needs.paths-filter.outputs.openaiChanged == 'true' ||
needs.paths-filter.outputs.coreChanged == 'true')
runs-on: ubuntu-latest
environment: integration
env:
OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Test with pytest (OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/openai/tests
-m "integration and not azure"
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
--junitxml=pytest.xml
working-directory: ./python
- name: Test OpenAI samples
timeout-minutes: 10
if: env.RUN_SAMPLES_TESTS == 'true'
run: uv run pytest tests/samples/ -m "openai"
working-directory: ./python
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: OpenAI integration test results
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: test-results-openai
path: ./python/pytest.xml
if-no-files-found: ignore
# Azure OpenAI integration tests
python-tests-azure-openai:
name: Python Tests - Azure OpenAI Integration
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true' &&
(github.event_name != 'merge_group' ||
needs.paths-filter.outputs.azureChanged == 'true' ||
needs.paths-filter.outputs.coreChanged == 'true')
runs-on: ubuntu-latest
environment: integration
env:
AZURE_OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_MODEL: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Azure CLI Login
if: github.event_name != 'pull_request'
uses: azure/login@v2
with:
client-id: ${{ secrets.AZURE_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Test with pytest (Azure OpenAI integration)
run: >
uv run pytest --import-mode=importlib
packages/openai/tests/openai/test_openai_chat_completion_client_azure.py
packages/openai/tests/openai/test_openai_chat_client_azure.py
packages/openai/tests/openai/test_openai_embedding_client_azure.py
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
--junitxml=pytest.xml
working-directory: ./python
- name: Test Azure samples
timeout-minutes: 10
if: env.RUN_SAMPLES_TESTS == 'true'
run: uv run pytest tests/samples/ -m "azure"
working-directory: ./python
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: Azure OpenAI integration test results
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: test-results-azure-openai
path: ./python/pytest.xml
if-no-files-found: ignore
# Misc integration tests (Anthropic, Ollama, MCP)
python-tests-misc-integration:
name: Python Tests - Misc Integration
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true' &&
(github.event_name != 'merge_group' ||
needs.paths-filter.outputs.miscChanged == 'true' ||
needs.paths-filter.outputs.coreChanged == 'true')
runs-on: ubuntu-latest
environment: integration
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
ANTHROPIC_CHAT_MODEL: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
OLLAMA_MODEL: qwen2.5:1.5b
OLLAMA_EMBEDDING_MODEL: nomic-embed-text
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Install Ollama
run: curl -fsSL https://ollama.com/install.sh | sh
working-directory: .
- name: Cache Ollama models
uses: actions/cache@v4
with:
path: ~/.ollama/models
key: ollama-models-qwen2.5-1.5b-nomic-embed-text-v1
- name: Start Ollama and pull models
run: |
ollama serve &
for i in $(seq 1 30); do
if curl -sf http://localhost:11434/api/tags > /dev/null 2>&1; then
break
fi
sleep 1
done
ollama pull qwen2.5:1.5b
ollama pull nomic-embed-text
working-directory: .
- name: Start local MCP server
id: local-mcp
uses: ./.github/actions/setup-local-mcp-server
with:
fallback_url: ${{ env.LOCAL_MCP_URL }}
- name: Prefer local MCP URL when available
run: echo "LOCAL_MCP_URL=${{ steps.local-mcp.outputs.effective_url }}" >> "$GITHUB_ENV"
- name: Test with pytest (Anthropic, Hyperlight, Ollama, MCP integration)
run: >
uv run pytest --import-mode=importlib
packages/anthropic/tests
packages/hyperlight/tests
packages/ollama/tests
packages/core/tests/core/test_mcp.py
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 30
--junitxml=pytest.xml
working-directory: ./python
- name: Stop local MCP server
if: always()
shell: bash
run: |
set -euo pipefail
server_pid="${{ steps.local-mcp.outputs.pid }}"
if [[ -z "$server_pid" ]]; then
exit 0
fi
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
kill -TERM -- "-$server_pid" 2>/dev/null || kill -TERM "$server_pid" 2>/dev/null || true
for _ in $(seq 1 10); do
if ! kill -0 "$server_pid" 2>/dev/null; then
exit 0
fi
sleep 1
done
kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: Misc integration test results
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: test-results-misc
path: ./python/pytest.xml
if-no-files-found: ignore
# Azure Functions + Durable Task integration tests
python-tests-functions:
name: Python Tests - Functions Integration
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true' &&
(github.event_name != 'merge_group' ||
needs.paths-filter.outputs.functionsChanged == 'true' ||
needs.paths-filter.outputs.coreChanged == 'true')
runs-on: ubuntu-latest
environment: integration
env:
UV_PYTHON: "3.11"
OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_CHAT_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
FUNCTIONS_WORKER_RUNTIME: "python"
DURABLE_TASK_SCHEDULER_CONNECTION_STRING: "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None"
AzureWebJobsStorage: "UseDevelopmentStorage=true"
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Azure CLI Login
if: github.event_name != 'pull_request'
uses: azure/login@v2
with:
client-id: ${{ secrets.AZURE_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Set up Azure Functions Integration Test Emulators
uses: ./.github/actions/azure-functions-integration-setup
id: azure-functions-setup
- name: Test with pytest (Functions + Durable Task integration)
run: >
uv run pytest --import-mode=importlib
packages/azurefunctions/tests/integration_tests
packages/durabletask/tests/integration_tests
-m integration
-n logical --dist worksteal
-x
--timeout=360 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
--junitxml=pytest.xml
working-directory: ./python
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: Functions integration test results
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: test-results-functions
path: ./python/pytest.xml
if-no-files-found: ignore
python-tests-foundry:
name: Python Integration Tests - Foundry
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true' &&
(github.event_name != 'merge_group' ||
needs.paths-filter.outputs.foundryChanged == 'true' ||
needs.paths-filter.outputs.coreChanged == 'true')
runs-on: ubuntu-latest
environment: integration
env:
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
FOUNDRY_MODELS_ENDPOINT: ${{ vars.FOUNDRY_MODELS_ENDPOINT || '' }}
FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY || '' }}
FOUNDRY_EMBEDDING_MODEL: ${{ vars.FOUNDRY_EMBEDDING_MODEL || '' }}
FOUNDRY_IMAGE_EMBEDDING_MODEL: ${{ vars.FOUNDRY_IMAGE_EMBEDDING_MODEL || '' }}
LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Azure CLI Login
if: github.event_name != 'pull_request'
uses: azure/login@v2
with:
client-id: ${{ secrets.AZURE_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: Test with pytest
timeout-minutes: 15
run: >
uv run pytest --import-mode=importlib
packages/foundry/tests
-m integration
-n logical --dist worksteal
--timeout=120 --session-timeout=900 --timeout_method thread
--retries 2 --retry-delay 5
--junitxml=pytest.xml
working-directory: ./python
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: Test results
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: test-results-foundry
path: ./python/pytest.xml
if-no-files-found: ignore
# TODO: Add python-tests-lab
# Azure Cosmos integration tests
python-tests-cosmos:
name: Python Tests - Cosmos Integration
needs: paths-filter
if: >
github.event_name != 'pull_request' &&
needs.paths-filter.outputs.pythonChanges == 'true' &&
(github.event_name != 'merge_group' ||
needs.paths-filter.outputs.cosmosChanged == 'true' ||
needs.paths-filter.outputs.coreChanged == 'true')
runs-on: ubuntu-latest
environment: integration
services:
cosmosdb:
image: mcr.microsoft.com/cosmosdb/linux/azure-cosmos-emulator:vnext-preview
ports:
- 8081:8081
env:
AZURE_COSMOS_ENDPOINT: "http://localhost:8081/"
# Static Azure Cosmos DB emulator key (documented): https://learn.microsoft.com/en-us/azure/cosmos-db/emulator
AZURE_COSMOS_KEY: "C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw=="
AZURE_COSMOS_DATABASE_NAME: "agent-framework-cosmos-it-db"
AZURE_COSMOS_CONTAINER_NAME: "agent-framework-cosmos-it-container"
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
id: python-setup
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Wait for Cosmos DB emulator
run: |
for i in {1..60}; do
if curl --silent --show-error http://localhost:8081/ > /dev/null; then
echo "Cosmos DB emulator is ready."
exit 0
fi
sleep 2
done
echo "Cosmos DB emulator did not become ready in time." >&2
exit 1
- name: Test with pytest (Cosmos integration)
run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
working-directory: ./python
- name: Surface failing tests
if: always()
uses: pmeier/pytest-results-action@v0.7.2
with:
path: ./python/pytest.xml
summary: true
display-options: fEX
fail-on-empty: false
title: Cosmos integration test results
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: test-results-cosmos
path: ./python/pytest.xml
if-no-files-found: ignore
# Integration test trend report (aggregates per-job JUnit XML results)
python-integration-test-report:
name: Integration Test Report
if: >
always() &&
(contains(join(needs.*.result, ','), 'success') ||
contains(join(needs.*.result, ','), 'failure'))
needs:
[
python-tests-openai,
python-tests-azure-openai,
python-tests-misc-integration,
python-tests-functions,
python-tests-foundry,
python-tests-cosmos,
]
runs-on: ubuntu-latest
defaults:
run:
working-directory: python
steps:
- uses: actions/checkout@v6
- name: Set up python and install the project
uses: ./.github/actions/python-setup
with:
python-version: ${{ env.UV_PYTHON }}
os: ${{ runner.os }}
- name: Download all test results from current run
uses: actions/download-artifact@v4
with:
pattern: test-results-*
path: test-results/
- name: Restore report history cache
uses: actions/cache/restore@v4
with:
path: python/integration-report-history.json
key: integration-report-history-merge-${{ github.run_id }}
restore-keys: |
integration-report-history-merge-
- name: Generate trend report
run: >
uv run python scripts/flaky_report/aggregate.py
../test-results/
integration-report-history.json
integration-test-report.md
- name: Post to Job Summary
if: always()
run: cat integration-test-report.md >> $GITHUB_STEP_SUMMARY
- name: Save report history cache
if: always()
uses: actions/cache/save@v4
with:
path: python/integration-report-history.json
key: integration-report-history-merge-${{ github.run_id }}
- name: Upload unified trend report
if: always()
uses: actions/upload-artifact@v7
with:
name: integration-test-report
path: |
python/integration-test-report.md
python/integration-report-history.json
python-integration-tests-check:
if: always()
runs-on: ubuntu-latest
needs:
[
python-tests-unit,
python-tests-openai,
python-tests-azure-openai,
python-tests-misc-integration,
python-tests-functions,
python-tests-foundry,
python-tests-cosmos,
]
steps:
- name: Fail workflow if tests failed
id: check_tests_failed
if: contains(join(needs.*.result, ','), 'failure')
uses: actions/github-script@v8
with:
script: core.setFailed('Integration Tests Failed!')
- name: Fail workflow if tests cancelled
id: check_tests_cancelled
if: contains(join(needs.*.result, ','), 'cancelled')
uses: actions/github-script@v8
with:
script: core.setFailed('Integration Tests Cancelled!')